Deploy Custom Models
Learn how to deploy a custom model on Tune Studio.
You can leverage open-source models or integrated API models as the foundation for deploying your custom models.
To deploy an open-source model (like Llama 3 or Open Hermes 2) or an API model (like Claude 3 Opus or ChatGPT-4), you’ll need a Tune Studio account with sufficient wallet credit.
You can deploy more models provided you maintain sufficient wallet balance Or by upgrading to Tune Studio Pro.
For API models, you’ll also need an API key from the respective Model Provider.
Both free and Pro plans allow model deployments, but deployments on the free plan are limited to 3 models and requires wallet credits.
Prerequisites
- A Tune Studio account (Free or Pro plan).
- Free Plan: Limited to 3 model deployments, provided you have sufficient wallet credit.
- Pro Plan: Supports additional features and higher deployment limits.
- An API key from the model provider (if deploying an integrated API model).
Step 1: Navigate to Models in Tune Studio
To deploy an integrated API model, navigate to the Models tab in the Tune Studio dashboard.
Click the ”+ New model” button to open the New model dialog.
Step 2: Select a Model Provider and Enter API Key
Select the model provider from the options under Integrations section. Enter your API key and click “Create”.
In this example, we selected OpenAI.
Step 3: Choose and Add Your Custom Model
Select the model to use (for example, GPT-4), give your custom model a name, and click “Add Model”.
Step 4: Access and Use the Model ID
Your new custom model will be created and brought online.
Use the custom model’s Model ID in text and chat completions to generate logs.
Locate the Model ID by clicking the three-dot icon next to the model name and selecting “Dashboard” from the dropdown.
The “Model ID” can be copied from the model detail view.
Your custom model is now fully deployed and ready to integrate into your application.
Next Steps
- Test Your Model: Use the deployed custom model in text and chat completions to verify its functionality.
- Generate Logs: Review logs for testing and debugging purposes.
Additional Resources
- API Documentation: Learn how to integrate and use the API for your custom models.
- Model Provider Guidelines: Review specific setup instructions for providers like OpenAI or Anthropic.
- Pricing and Model Support: Understand model pricing and supported models.
Was this page helpful?